pycsamt.ai.inversion.inv1d#

End-to-end 1-D EM inversion workflow.

EMInverter1D is the primary user-facing estimator for 1-D neural-network inversion of MT, CSAMT, and TEM data. It:

  1. Loads a ForwardDataset (or a .npz path to one).

  2. Normalises features and targets with z-score normalisation (log₁₀ thickness transform applied automatically).

  3. Instantiates the requested architecture ('cnn1d', 'resnet', 'fcn').

  4. Trains with EMTrainer (early stopping, LR scheduling, masked MSE loss).

  5. Predicts on new data as: * numpy arrays * lists of Z objects * ForwardResponse objects

The sklearn-compatible interface (fit / predict / score) from BaseEMNet is preserved.

Quick start#

>>> import numpy as np
>>> from pycsamt.forward.batch import generate_dataset
>>> from pycsamt.ai.inversion.inv1d import EMInverter1D

# Generate 2 000 training samples >>> ds = generate_dataset(n_samples=2_000, seed=0, n_layers=5)

# Train >>> inv = EMInverter1D(arch=”resnet”, n_layers=5, solver=”mt1d”) >>> inv.fit(ds, epochs=30, batch_size=128, verbose=True)

# Predict on a new forward response >>> from pycsamt.forward import MT1DForward, LayeredModel >>> m_new = LayeredModel.random(n_layers=5, seed=99) >>> resp = MT1DForward(np.logspace(-3, 4, 30)).run(m_new) >>> y_pred = inv.predict_response(resp) # → LayeredModel

Classes

EMInverter1D([arch, n_layers, solver, ...])

1-D EM neural-network inverter.
class pycsamt.ai.inversion.inv1d.EMInverter1D(arch='resnet', n_layers=5, solver='mt1d', *, device=None, log_thickness=True, include_phase=True, augment_noise=0.02, **net_kwargs)[source]#

Bases: BaseEMNet

1-D EM neural-network inverter.

Supports MT, CSAMT (far-field), and TEM step-off data.

Parameters:

  • arch ({'resnet', 'cnn1d', 'fcn'}) – Network architecture. 'resnet' (Liu 2021 style) gives the best accuracy on typical MT datasets. 'cnn1d' (Puzyrev style) is faster to train. 'fcn' (Moghadas style) handles variable input length.

  • n_layers (int) – Number of earth layers to invert for.

  • solver ({'mt1d', 'csamt1d', 'tem1d'}) – EM method this inverter targets (determines default frequency grid for Z-object input coercion).

  • device (str or None) – Compute device. Auto-detects CUDA/MPS/CPU if None.

  • log_thickness (bool) – Apply log₁₀ to thickness in training targets. Strongly recommended when thicknesses span > 2 orders of magnitude.

  • include_phase (bool) – Include impedance phase in the input feature vector for MT/CSAMT. Setting to False halves the input size.

  • augment_noise (float) – On-the-fly noise level added to training inputs each epoch.

  • net_kwargs (dict) – Extra keyword arguments forwarded to the network constructor (e.g. channels=(64, 128, 256) for ResNet).

fit(X, y=None, *, epochs=100, batch_size=256, lr=0.001, patience=20, val_frac=0.1, grad_clip=1.0, seed=None, verbose=True)[source]#

Train the inverter on a ForwardDataset or a .npz file path.

Parameters:

  • X (ForwardDataset or str or Path) – Training data. If y is also given, X and y are treated as raw feature / target numpy arrays.

  • y (ndarray or None) – Raw targets (only when X is an ndarray).

  • epochs (int) – Maximum training epochs.

  • batch_size (int)

  • lr (float) – Initial learning rate.

  • patience (int) – Early-stopping patience.

  • val_frac (float) – Fraction of training data used for validation.

  • grad_clip (float or None) – Gradient-norm clipping threshold.

  • seed (int or None) – Random seed for train/val split.

  • verbose (bool) – Print per-epoch summary.

Return type:

self

predict(X, *, as_log_rho=True)[source]#

Predict model parameters for new data.

Parameters:

  • X (ndarray (n_samples, n_features) | Z | list of Z | ForwardResponse) – Input data.

  • as_log_rho (bool) – If True (default), the returned resistivity values are in log₁₀(Ω·m) space matching the training targets. If False, resistivities are back-transformed to Ω·m.

Returns:

y_pred – Parameter vector: [log10(ρ), log10(h)] (or linear if as_log_rho=False).

Return type:

ndarray, shape (n_samples, n_params)

predict_models(X)[source]#

Predict and return a list of LayeredModel.

Resistivity and thickness are back-transformed from log space.

Return type:

list

predict_response(response)[source]#

Convenience: invert a single ForwardResponse and return the predicted LayeredModel.

Return type:

LayeredModel

save(path)[source]#

Save weights + normaliser + hyperparameters to path.

Parameters:

path (str | Path)

Return type:

None

classmethod load(path)[source]#

Load a saved inverter from path.

Parameters:

path (str | Path)

Return type:

EMInverter1D

classmethod from_pretrained(name, *, cache_dir=None)[source]#

Load a pre-trained model from the pycsamt model zoo.

Pre-trained weights are hosted at earthai-tech/pycsamt-models and are downloaded to ~/.pycsamt/model_zoo/ on first call.

Parameters:

  • name (str) – Model identifier. Call list_pretrained() to see available models.

  • cache_dir (str or None) – Override the default download directory.

Return type:

EMInverter1D

Raises:

  • KeyError – If name is not in the model zoo registry.

  • RuntimeError – If the download fails (weights not yet publicly available).

Examples

>>> from pycsamt.ai.inversion import EMInverter1D
>>> inv = EMInverter1D.from_pretrained("mt1d-resnet-5layer-v1")